A high-storage capacity content-addressable memory and its learning algorithm

J.J. Hopfield´s neural networks (1982) show retrieval and speed capabilities that make them good candidates for content-addressable memories (CAMs) in problems such as pattern recognition and optimization. A novel implementation is presented of a VLSI fully interconnected neural network with only two binary memory points per synapse (the connection weights are restricted to three different values: +1, 0 and -1). The small area of single synaptic cells (about 10 ⁴ μm²) allows the implementation of neural networks with more than 500 neurons. Because of the poor storage capability of D. Hebb´s learning rule (1949), especially in VLSI neural networks where the range of the synapse weights is limited by the number of memory points contained in each connection, a novel algorithm is proposed for programming a Hopfield neural network as a high-storage-capacity CAM. The results of the VLSI circuit programmed with this algorithm are very promising for pattern-recognition applications